One would think semantic density would win out in training.
Close out previous paragraph. Segue to completely different topic.
How else are you supposed to go on a tangent?
It’s also annoying as a human because Claude et al rate their own writing very highly, putting human<>LLM interactions at a disadvantage to human->LLM<>LLM interactions.
First, "the hardest lesson". What lesson? It is out of context. Nobody was talking about lessons before this.
Second, "the bottleneck wasn't what we were measuring and observing". Of course the bottleneck itself wasn't that. They couldn't discover what the bottleneck was using the information in their measurements and observations.
It is a clunky and frankly incorrect passage in an otherwise well written article.
But it suuucks, making it hard to read, the same way (some) fast/junk food is hard to swallow.
They have access to a trillion dollar writing machine god, and they choose to publish that.